厨房电器设备非侵入式粒子群搜索辨识及参数优化方法研究  

Research on Kitchen Electrical Equipment Identification and Parameter Optimization Method by PSO Based on NIML

作　　者：张云翔 赵少东 饶竹一 秦毅 吴恒 ZHANG Yunxiang;ZHAO Shaodong;RAO Zhuyi;QING Yi;WU Heng(China Southern Power Grid Shenzhen Electric Power Supply Company,Shenzhen 518001,China;Shenzhen Micro-net Energy Management System Laboratory Co.,Ltd.,Shenzhen 518001,China;Jiangsu Zhi Zhen Energy Technology Co.,Ltd.,Nanjing 211100,China)

机构地区：[1]南方电网深圳供电局有限公司,广东深圳518001 [2]深圳微网能源管理系统实验室有限公司,广东深圳518001 [3]江苏智臻能源科技有限公司,江苏南京211100

出　　处：《电器与能效管理技术》2019年第2期25-31,37,共8页Electrical & Energy Management Technology

摘　　要：为了挖掘居民负荷参与需求侧响应的潜力,避免侵入式量测在居民负荷采集难以推广的问题,提出基于非侵入量测通过粒子群算法对非侵入量测关口的电气量稳态特征进行搜索辨识的方法。为解决多特征量中以单一特征量辨识准确率低,而多特征量综合辨识的系数难以确定的问题,提出了综合特征量适应度函数和辨识系数优化方法。最后,基于一组算例验证了所提方法的有效性,能够有效提高通过稳态量进行厨房设备辨识的准确率。In order to explore the potential of residents’load to participate the demand side response and avoid the problem that intrusive load monitoring(ILM)is difficult to popularize in residential load collection,a method based on non-intrusive load monitoring(NILM)was proposed to search and identify the steady-state characteristics of the gate through particle swarm optimization(PSO).Furthermore,an optimization method of identification coefficient was proposed,to solve the problem of low identification accuracy rate based on single in multi-feature and difficult to determine the identification coefficient of comprehensive of multi-feature quantity.Finally,the effectiveness of the proposed method was verified based on a set of examples,which can effectively improve the accuracy rate of kitchen equipment identification through electrical steady-state characteristics.

关 键 词：需求侧响应 非侵入量测 粒子群算法 参数优化 

分 类 号：TM714[电气工程—电力系统及自动化]